Litcius/Paper detail

The GroupMax Neural Network Approximation of Convex Functions

Xavier Warin

2023IEEE Transactions on Neural Networks and Learning Systems16 citationsDOI

Abstract

We present a new neural network to approximate convex functions. This network has the particularity to approximate the function with cuts which is, for example, a necessary feature to approximate Bellman values when solving linear stochastic optimization problems. The network can be easily adapted to partial convexity. We give an universal approximation theorem in the full convex case and give many numerical results proving its efficiency. The network is competitive with the most efficient convexity-preserving neural networks and can be used to approximate functions in high dimensions.

Topics & Concepts

ConvexityArtificial neural networkConvex functionConvex analysisMathematicsRegular polygonMathematical optimizationConvex optimizationFunction (biology)Computer scienceStochastic neural networkProper convex functionApplied mathematicsRecurrent neural networkArtificial intelligenceEvolutionary biologyEconomicsGeometryBiologyFinancial economicsNeural Networks and ApplicationsModel Reduction and Neural NetworksStochastic Gradient Optimization Techniques
The GroupMax Neural Network Approximation of Convex Functions | Litcius